Elimination of experimentation cost and time by data analysis in mechanical property prediction of aluminum alloys

Abstract

Discovery of new materials in material science involves lot of processes like experimental trials and laboratory testing which consumes lot of time and energy. This process requires theoretical foundation to avoid errors and also constrained by laboratory environment conditions. To overcome the above issues, data analysis techniques are used for material property prediction for the new materials which reduces lot of time and energy by avoiding experimentation. Plenty of data is available in the material science field for the analysis. In this work, Aluminum alloy composite properties are collected and analysed for the mechanical property prediction. Data available in this case is the labelled data and the output is a continuous variable, so the supervised regression algorithms such as linear regression (LR), K- Nearest Neighbor algorithm (KNN) and Artificial Neural Network (ANN) are proposed for the tensile strength prediction of aluminum alloys. The performance of LR, KNN and ANN are measured in terms of R2 value respectively 90.5%, 96.5% and 89%. K-Nearest Neighbor algorithm is selected as best algorithm because of its accurate prediction and the testing data is varied between 10 and 30 percentage and the R-square values are calculated for 10, 20 and 30 percentage of test size are 94.3%, 93.2% and 96.3%. Best algorithm with proper test size is found using above methodology. Similar methodology can be applied for predicting the other properties of aluminum composites and also for other composites.